Image to text (OCR) in English and Urdu

Copy the text out of a photo, a screenshot or a scanned PDF instead of typing it again. Choose English, Urdu, or both. Everything runs in your browser, so documents are not uploaded anywhere.

How to use it

1. Drop one or more images, or a scanned PDF (up to 20 pages).
2. Choose the language of the text.
3. Click Get the text. The first time, the reader downloads its language data (about 3 MB for English, 1 MB for Urdu).
4. Copy the text or download it as a .txt file. Check names and numbers before you rely on them.

What works well

• Printed or typed text, photographed straight and in good light, or clean scans.
• Urdu typed in standard computer fonts, such as most forms and Word documents.

What is harder

• Handwriting is not supported.
• Urdu in Nastaliq calligraphy style, as in many newspapers and books, is read much less accurately.
• Tables come out as plain lines of text. For PDFs with real tables, try PDF to Excel.